PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound: A link between carotid and coronary grayscale plaque morphology

BACKGROUND AND OBJECTIVE Percutaneous coronary interventional procedures need advance planning prior to stenting or an endarterectomy. Cardiologists use intravascular ultrasound (IVUS) for screening, risk assessment and stratification of coronary artery disease (CAD). We hypothesize that plaque components are vulnerable to rupture due to plaque progression. Currently, there are no standard grayscale IVUS tools for risk assessment of plaque rupture. This paper presents a novel strategy for risk stratification based on plaque morphology embedded with principal component analysis (PCA) for plaque feature dimensionality reduction and dominant feature selection technique. The risk assessment utilizes 56 grayscale coronary features in a machine learning framework while linking information from carotid and coronary plaque burdens due to their common genetic makeup. METHOD This system consists of a machine learning paradigm which uses a support vector machine (SVM) combined with PCA for optimal and dominant coronary artery morphological feature extraction. Carotid artery proven intima-media thickness (cIMT) biomarker is adapted as a gold standard during the training phase of the machine learning system. For the performance evaluation, K-fold cross validation protocol is adapted with 20 trials per fold. For choosing the dominant features out of the 56 grayscale features, a polling strategy of PCA is adapted where the original value of the features is unaltered. Different protocols are designed for establishing the stability and reliability criteria of the coronary risk assessment system (cRAS). RESULTS Using the PCA-based machine learning paradigm and cross-validation protocol, a classification accuracy of 98.43% (AUC 0.98) with K=10 folds using an SVM radial basis function (RBF) kernel was achieved. A reliability index of 97.32% and machine learning stability criteria of 5% were met for the cRAS. CONCLUSIONS This is the first Computer aided design (CADx) system of its kind that is able to demonstrate the ability of coronary risk assessment and stratification while demonstrating a successful design of the machine learning system based on our assumptions.

[1]  Fengxi Song,et al.  Feature Selection Using Principal Component Analysis , 2010, 2010 International Conference on System Science, Engineering Design and Manufacturing Informatization.

[2]  Abdus Sattar,et al.  Relation of carotid intima-media thickness and plaque with incident cardiovascular events in women with systemic lupus erythematosus. , 2013, The American journal of cardiology.

[3]  Diederick E Grobbee,et al.  Carotid intima-media thickness and coronary atherosclerosis: weak or strong relations? , 2007, European heart journal.

[4]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[5]  R O Bonow,et al.  Contrast magnetic resonance imaging in the assessment of myocardial viability in patients with stable coronary artery disease and left ventricular dysfunction. , 1998, Circulation.

[6]  Filippo Molinari,et al.  Shape‐Based Approach for Coronary Calcium Lesion Volume Measurement on Intravascular Ultrasound Imaging and Its Association With Carotid Intima‐Media Thickness , 2015, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[7]  Nilanjan Dey,et al.  A comparative approach of four different image registration techniques for quantitative assessment of coronary artery calcium lesions using intravascular ultrasound , 2015, Comput. Methods Programs Biomed..

[8]  W. Tracz,et al.  Association of increased carotid intima-media thickness with the extent of coronary artery disease , 2004, Heart.

[9]  Shigeru Oshima,et al.  Coronary artery calcification as a new predictor of non-target lesion revascularization during the chronic phase after successful percutaneous coronary intervention , 2014, Cardiovascular Intervention and Therapeutics.

[10]  Nassir Navab,et al.  A State-of-the-Art Review on Segmentation Algorithms in Intravascular Ultrasound (IVUS) Images , 2012, IEEE Transactions on Information Technology in Biomedicine.

[11]  K. Nishigaki,et al.  Development of integrated backscatter intravascular ultrasound for tissue characterization of coronary plaques. , 2008, Ultrasound in medicine & biology.

[12]  Ewout W Steyerberg,et al.  Common carotid intima-media thickness in cardiovascular risk stratification of older people: the Rotterdam Study , 2012, European journal of preventive cardiology.

[13]  Spyretta Golemati,et al.  Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks. , 2007, Ultrasound in medicine & biology.

[14]  Constantinos S. Pattichis,et al.  Texture-based classification of atherosclerotic carotid plaques , 2003, IEEE Transactions on Medical Imaging.

[15]  E. Halpern,et al.  Characterization of Human Atherosclerosis by Optical Coherence Tomography , 2002, Circulation.

[16]  Richard D. White,et al.  Coronary imaging: angiography shows the stenosis, but IVUS, CT, and MRI show the plaque. , 2003, Cleveland Clinic journal of medicine.

[17]  Elena Tremoli,et al.  Carotid intima-media thickness by B-mode ultrasound as surrogate of coronary atherosclerosis: correlation with quantitative coronary angiography and coronary intravascular ultrasound findings. , 2007, European heart journal.

[18]  J. Borén,et al.  Ira Tabas , Kevin Jon Williams and Jan Borén and Therapeutic Implications Subendothelial Lipoprotein Retention as the Initiating Process in Atherosclerosis : Update , 2007 .

[19]  Tae Jin Lee,et al.  DICOM-based intravascular ultrasound signal intensity analysis: an Echoplaque Medical Imaging Bench study , 2014, Coronary artery disease.

[20]  Tadashi Araki,et al.  Visualization of coronary plaque in arterial remodeling using a new 40‐MHz intravascular ultrasound imaging system , 2013, Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions.

[21]  Paul Schoenhagen,et al.  Understanding coronary artery disease: tomographic imaging with intravascular ultrasound , 2002, Heart.

[22]  Filippo Molinari,et al.  An automated technique for carotid far wall classification using grayscale features and wall thickness variability , 2015, Journal of clinical ultrasound : JCU.

[23]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[24]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[25]  U. Rajendra Acharya,et al.  Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment , 2013, Medical & Biological Engineering & Computing.

[26]  J. Leipsic,et al.  Do plaques rapidly progress prior to myocardial infarction? The interplay between plaque vulnerability and progression. , 2015, Circulation research.

[27]  E. Tuzcu,et al.  Coronary Plaque Classification With Intravascular Ultrasound Radiofrequency Data Analysis , 2002, Circulation.

[28]  N Bom,et al.  Characterization of plaque components with intravascular ultrasound elastography in human femoral and coronary arteries in vitro. , 2000, Circulation.

[29]  Michael J Pencina,et al.  Associations of Edge-Detected and Manual-Traced Common Carotid Intima-Media Thickness Measurements With Framingham Risk Factors: The Multi-Ethnic Study of Atherosclerosis , 2011, Stroke.

[30]  V. Fuster,et al.  Coronary plaque disruption. , 1995, Circulation.

[31]  J. Suri,et al.  Improved correlation between carotid and coronary atherosclerosis SYNTAX score using automated ultrasound carotid bulb plaque IMT measurement. , 2015, Ultrasound in medicine & biology.

[32]  Jasjit S. Suri,et al.  A new method for IVUS-based coronary artery disease risk stratification: A link between coronary & carotid ultrasound plaque burdens , 2016, Comput. Methods Programs Biomed..

[33]  J. Suri,et al.  Atherosclerotic risk stratification strategy for carotid arteries using texture-based features. , 2012, Ultrasound in medicine & biology.

[34]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[35]  Nobutaka Ikeda,et al.  Impact of carotid artery ultrasound and ankle-brachial index on prediction of severity of SYNTAX score. , 2013, Circulation journal : official journal of the Japanese Circulation Society.

[36]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[37]  Jasjit S. Suri,et al.  Reliable and accurate psoriasis disease classification in dermatology images using comprehensive feature space in machine learning paradigm , 2015, Expert Syst. Appl..

[38]  P Krishna Kumar,et al.  A Review on Carotid Ultrasound Atherosclerotic Tissue Characterization and Stroke Risk Stratification in Machine Learning Framework , 2015, Current Atherosclerosis Reports.

[39]  R. Ross,et al.  Cell biology of atherosclerosis. , 1995, Annual review of physiology.

[40]  Derek Abbott,et al.  Surface Roughness Detection of Arteries via Texture Analysis of Ultrasound Images for Early Diagnosis of Atherosclerosis , 2013, PloS one.

[41]  U. Rajendra Acharya,et al.  Symptomatic vs. Asymptomatic Plaque Classification in Carotid Ultrasound , 2012, Journal of Medical Systems.

[42]  I. Kallikazaros,et al.  Carotid artery disease as a marker for the presence of severe coronary artery disease in patients evaluated for chest pain. , 1999, Stroke.

[43]  Osamu Seguchi,et al.  Atherosclerosis Found on Carotid Ultrasonography Is Associated With Atherosclerosis on Coronary Intravascular Ultrasonography , 2005, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[44]  L. Athanasiou,et al.  Atherosclerotic plaque characterization using geometrical features from virtual histology intravascular ultrasound images , 2010, Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine.

[45]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[46]  Jasjit S. Suri,et al.  First review on psoriasis severity risk stratification: An engineering perspective , 2015, Comput. Biol. Medicine.

[47]  Abhay Chowdhary,et al.  Artificial Neural Network Application in the Diagnosis of Disease Conditions with Liver Ultrasound Images , 2014, Adv. Bioinformatics.

[48]  Nassir Navab,et al.  New Approaches for Plaque Component Analysis in Intravascular Ultrasound (IVUS) Images , 2014 .

[49]  Boudewijn P. F. Lelieveldt,et al.  Automatic quantification and characterization of coronary atherosclerosis with computed tomography coronary angiography: cross-correlation with intravascular ultrasound virtual histology , 2013, The International Journal of Cardiovascular Imaging.

[50]  J. Suri,et al.  Advanced algorithmic approaches to medical image segmentation: state-of-the-art application in cardiology, neurology, mammography and pathology , 2001 .

[51]  Michael J Pencina,et al.  Associations of Carotid Artery Intima‐Media Thickness (IMT) With Risk Factors and Prevalent Cardiovascular Disease , 2010, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.